Silicon is the primary semiconductor material used to fabricate microchips. The quality of microchips depends directly on the quality of the starting silicon wafers. One of the manufacturing problems in the manufacturing of silicon wafers is the presence of waviness on the surface as a result of wire-sawn slicing. To reduce this waviness, soft-pad grinding, a patented method, is used. Many factors influence the waviness reduction capacity during soft-pad grinding. The method of finite element analysis has been used to analyze the various factors. However, the grinding process is very complicated, the various factors are very vague and difficult to define. In this research, the recently developed fuzzy-neural adaptive network, which is ideally suited for the modeling of vague phenomenon, is used to model and to improve this waviness problem. To illustrate the usefulness of the approach, the process is modeled based on simulation data. The results, even though based on some very limited data, illustrate the influences of the various factors clearly.
Application of Fuzzy Adaptive Networks in Manufacturing: Waviness Removal in Grinding of Wire-Sawn Silicon Wafers
- Views Icon Views
- Share Icon Share
- Search Site
Jiao, Y, Wu, J, Lei, S, Pei, ZJ, & Lee, ES. "Application of Fuzzy Adaptive Networks in Manufacturing: Waviness Removal in Grinding of Wire-Sawn Silicon Wafers." Proceedings of the ASME 2003 International Mechanical Engineering Congress and Exposition. Manufacturing. Washington, DC, USA. November 15–21, 2003. pp. 643-652. ASME. https://doi.org/10.1115/IMECE2003-41821
Download citation file: